Seamless lightning nowcasting with recurrent-convolutional deep learning

TL;DR

This paper introduces a deep learning model that predicts lightning occurrence up to 60 minutes ahead using a recurrent-convolutional architecture on radar, satellite, and weather data, without storm object detection.

Contribution

The study presents a novel recurrent-convolutional deep learning approach for lightning nowcasting that effectively models spatiotemporal convection development without storm tracking.

Findings

Achieves a CSI of 0.45 at 60-minute lead time

Focal loss offers slight improvement over cross entropy

Model effectively predicts lightning with 5-minute lead time CSI of 0.75

Abstract

A deep learning model is presented to nowcast the occurrence of lightning at a five-minute time resolution 60 minutes into the future. The model is based on a recurrent-convolutional architecture that allows it to recognize and predict the spatiotemporal development of convection, including the motion, growth and decay of thunderstorm cells. The predictions are performed on a stationary grid, without the use of storm object detection and tracking. The input data, collected from an area in and surrounding Switzerland, comprise ground-based radar data, visible/infrared satellite data and derived cloud products, lightning detection, numerical weather prediction and digital elevation model data. We analyze different alternative loss functions, class weighting strategies and model features, providing guidelines for future studies to select loss functions optimally and to properly calibrate the probabilistic predictions of their model. Based on these analyses, we use focal loss in this study, but conclude that it only provides a small benefit over cross entropy, which is a viable option if recalibration of the model is not practical. The model achieves a pixel-wise critical success index (CSI) of 0.45 to predict lightning occurrence within 8 km over the 60-min nowcast period, ranging from a CSI of 0.75 at a 5-min lead time to a CSI of 0.32 at a 60-min lead time.